Flex
Not every answer is needed right now. Tell Zabio how long you can wait, and it uses the cheaper, slower tiers vendors offer, without ever letting that make your request fail.
The video loads from YouTube only when you press play.
- About 50%off on OpenAI and Google models that offer a flex tier
- 20 vs 40micros for the same gpt-5.4-nano call, flex against standard, in our tests
- 0requests failed because of flex: a capacity refusal is retried at the normal tier
How to ask
- Send zabio.deadline with a duration, such as 30m, or the header x-zabio-deadline.
- 15 minutes or more lets Zabio use flex where the model has it.
- Under auto, candidates are compared at their flex prices, so a model can win because it is cheaper in flex.
- Raise your SDK timeout to at least 900 seconds, since a flex call can take longer than the default.
What it costs
- You pay the flex price for calls that ran on flex, and the normal price when a vendor had no capacity and Zabio retried at the normal tier.
- Your saving is measured against the flex price of your baseline, so it never counts the vendor's discount as routing's work.
For big jobs: batching
- For thousands of requests that can wait hours, send them as one file with batching, at the vendors' batch prices.
Questions
- Can I pay less when I am not in a hurry?
- Yes. Send zabio.deadline with a duration of 15 minutes or more, for example "30m", and Zabio serves the call on the flex tier of OpenAI or Google where the model has one, at about half the price. Under auto, candidates are compared at their flex prices. If the vendor has no capacity, Zabio retries at the normal tier and bills the price actually used, so a flex request never fails for that reason. Your saving is measured against the flex price of your usual model, so it never counts the vendor's discount as routing's work. For large jobs that can wait hours, batching sends a whole file at the vendors' batch prices.
Other features
Smart Splitting
One request, several models, a smaller bill, decided for you on every call. When we can save, we save.
Smart routing
The right model and reasoning setting for every request, picked from evidence, with the reason on every response.
Jev for classification
Tagging, routing, moderation and sentiment for a fraction of the price of a chat model, named or picked by auto.
Caching
Your history cached for you, the 1 hour cache when turns are slow, and never a cut of your cache discount.
Batching
Thousands of requests in one file at about half price, with auto routing on every line.
Teams and keys
Organizations, member quotas, keys with spend caps and model lists, and your own vendor keys with no service fee.
Start free, upgrade when it's real
Change two lines in your code, send model auto, and every response shows what it cost and what you saved.